Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 11961
    Prev
    Next
    INDEX
    Explanations

    World records

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bonita
    -0.08
     bookkeeping
    -0.08
     Moodle
    -0.08
    itlement
    -0.08
    厂
    -0.08
     Tuition
    -0.08
     Bulgar
    -0.08
     aban
    -0.08
    portunities
    -0.08
     boleto
    -0.08
    POSITIVE LOGITS
     Guinness
    0.12
     unprecedented
    0.10
     withstand
    0.10
    .timeout
    0.09
     overcoming
    0.09
    .speed
    0.09
     endurance
    0.09
     doğr
    0.09
    .duration
    0.09
     极
    0.08
    Activations Density 0.041%

    No Known Activations